Skip to content

feat(core): add support for gemini-3.8-flash as default flash model - #29172

Closed
mr8lu wants to merge 2 commits into
google-gemini:mainfrom
mr8lu:feat/support-gemini-3.8-flash
Closed

mr8lu wants to merge 2 commits into
google-gemini:mainfrom
mr8lu:feat/support-gemini-3.8-flash

Conversation

@mr8lu

@mr8lu mr8lu commented Sep 2, 2026

Copy link
Copy Markdown

Summary

  • Registers gemini-3.5-flash-lite, gemini-3.6-flash, gemini-3.7-flash, and gemini-3.8-flash as valid, selectable Gemini models (constants, VALID_GEMINI_MODELS, defaultModelConfigs.ts aliases/definitions/resolutions).
  • Promotes gemini-3.8-flash to the default flash model returned once the flash GA rollout experiment (hasGemini35FlashGAAccess) is active, replacing gemini-3.5-flash in that role.
  • Preserves explicit manual selection of any of the 3.5/3.6/3.7/3.8 flash models — they no longer get silently redirected to the default flash model.

Test plan

  • npx tsc --noEmit (core + cli) passes
  • npm run lint passes with zero warnings
  • Full models.test.ts, defaultModelConfigs, modelConfigService.test.ts, config.test.ts, coreToolsModelSnapshots.test.ts, and availability/* suites pass (480 tests)
  • Regenerated docs/reference/configuration.md and schemas/settings.schema.json from the updated model configs

🤖 Generated with Claude Code

@mr8lu
mr8lu requested review from a team as code owners September 2, 2026 22:31
@google-cla

google-cla Bot commented Sep 2, 2026

Copy link
Copy Markdown

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

@github-actions github-actions Bot added the size/l A large sized PR label Sep 2, 2026
@github-actions

github-actions Bot commented Sep 2, 2026 •

Copy link
Copy Markdown

📊 PR Size: size/L

  • Lines changed: 613
  • Additions: +563
  • Deletions: -50
  • Files changed: 10

@gemini-code-assist

Copy link
Copy Markdown
Contributor

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request expands the available Gemini model repertoire by registering several new flash variants and updating the default flash model target to gemini-3.8-flash for eligible users. The changes include updates to core configurations, CLI UI components, and test suites to ensure consistent behavior and support for these new models while maintaining existing manual selection capabilities.

Highlights

  • New Model Support: Added support for gemini-3.5-flash-lite, gemini-3.6-flash, gemini-3.7-flash, and gemini-3.8-flash.
  • Default Model Promotion: Promoted gemini-3.8-flash as the default flash model for users with GA access, replacing gemini-3.5-flash.
  • Manual Selection Preservation: Ensured that explicit manual selection of specific flash models is preserved and not subject to silent redirection.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize the Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the default Gemini Flash model from gemini-3.5-flash to gemini-3.8-flash across configuration files, schemas, tests, and UI components, and registers several new Gemini 3.x Flash models. The review feedback correctly identifies that the alternative name for the 3.5 Flash model (SECONDARY_GEMINI_3_5_FLASH_MODEL / 'gemini-3-flash') was omitted from the override exclusion check in resolveModel, which would cause manual selections of this model to be overridden. It is recommended to update this check and add a corresponding test case using hardcoded literal values to prevent regressions.

Comment on lines +240 to +245
normalizedModel !== PREVIEW_GEMINI_FLASH_MODEL &&
normalizedModel !== DEFAULT_GEMINI_3_5_FLASH_MODEL &&
normalizedModel !== GEMINI_3_5_FLASH_LITE_MODEL &&
normalizedModel !== GEMINI_3_6_FLASH_MODEL &&
normalizedModel !== GEMINI_3_7_FLASH_MODEL &&
normalizedModel !== GEMINI_3_8_FLASH_MODEL

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The alternative name for the 3.5 Flash model (SECONDARY_GEMINI_3_5_FLASH_MODEL / 'gemini-3-flash') is not excluded from the override check. This causes explicit manual selections of 'gemini-3-flash' to be silently redirected to gemini-3.8-flash when useGemini3_5Flash is active, violating the goal of preserving explicit manual selections of 3.5/3.6/3.7/3.8 flash models.

    normalizedModel !== PREVIEW_GEMINI_FLASH_MODEL &&
    normalizedModel !== DEFAULT_GEMINI_3_5_FLASH_MODEL &&
    normalizedModel !== SECONDARY_GEMINI_3_5_FLASH_MODEL &&
    normalizedModel !== GEMINI_3_5_FLASH_LITE_MODEL &&
    normalizedModel !== GEMINI_3_6_FLASH_MODEL &&
    normalizedModel !== GEMINI_3_7_FLASH_MODEL &&
    normalizedModel !== GEMINI_3_8_FLASH_MODEL

Comment on lines +872 to +881
expect(
resolveModel(
DEFAULT_GEMINI_3_5_FLASH_MODEL,
false,
false,
true,
undefined,
true,
),
).toBe(DEFAULT_GEMINI_3_5_FLASH_MODEL);

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

Add a test case to verify that explicit manual selections of the alternative 3.5 Flash model name ('gemini-3-flash') are preserved and not overridden when useGemini3_5Flash is active. In accordance with our testing guidelines, use hardcoded literal values instead of importing constants to ensure tests are self-contained and less brittle.

Suggested change
expect(
resolveModel(
DEFAULT_GEMINI_3_5_FLASH_MODEL,
false,
false,
true,
undefined,
true,
),
).toBe(DEFAULT_GEMINI_3_5_FLASH_MODEL);
expect(
resolveModel(
'gemini-3.5-flash',
false,
false,
true,
undefined,
true,
),
).toBe('gemini-3.5-flash');
expect(
resolveModel(
'gemini-3-flash',
false,
false,
true,
undefined,
true,
),
).toBe('gemini-3-flash');
References
  1. In tests, prefer using hardcoded literal values instead of importing constants to ensure tests are self-contained and less brittle.

@gemini-cli gemini-cli Bot added the status/need-issue Pull requests that need to have an associated issue. label Sep 2, 2026
@wissamblue69-dotcom

Copy link
Copy Markdown

Summary

  • Registers gemini-3.5-flash-lite, gemini-3.6-flash, gemini-3.7-flash, and gemini-3.8-flash as valid, selectable Gemini models (constants, VALID_GEMINI_MODELS, defaultModelConfigs.ts aliases/definitions/resolutions).
  • Promotes gemini-3.8-flash to the default flash model returned once the flash GA rollout experiment (hasGemini35FlashGAAccess) is active, replacing gemini-3.5-flash in that role.
  • Preserves explicit manual selection of any of the 3.5/3.6/3.7/3.8 flash models — they no longer get silently redirected to the default flash model.

Test plan

  • npx tsc --noEmit (core + cli) passes
  • npm run lint passes with zero warnings
  • Full models.test.ts, defaultModelConfigs, modelConfigService.test.ts, config.test.ts, coreToolsModelSnapshots.test.ts, and availability/* suites pass (480 tests)
  • Regenerated docs/reference/configuration.md and schemas/settings.schema.json from the updated model configs

🤖 Generated with Claude Code

…rollout

SECONDARY_GEMINI_3_5_FLASH_MODEL ('gemini-3-flash') was missing from the
override-exclusion list in resolveModel(), so explicitly selecting it while
the flash GA rollout is active silently redirected to the default flash
model instead of preserving the user's choice, same as the other flash
aliases.
@gemini-cli

gemini-cli Bot commented Sep 10, 2026

Copy link
Copy Markdown
Contributor

Hi there! Thank you for your interest in contributing to Gemini CLI.

To ensure we maintain high code quality and focus on our prioritized roadmap, we only guarantee review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'.

This PR will be closed in 7 days if it remains without that designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.

@gemini-cli

gemini-cli Bot commented Sep 17, 2026

Copy link
Copy Markdown
Contributor

This pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size/l A large sized PR status/need-issue Pull requests that need to have an associated issue. status/pr-nudge-sent

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants